What is 'Gradients' in the context of ML?

What is 'Gradients' in the context of ML?

Approach: Define the vector of partial derivatives.

A vector of partial derivatives of a function. In machine learning, the gradient of the loss function points in the direction of the steepest increase; we move in the opposite direction to minimize the loss.

Follow-up: What is a 'zero gradient'?

Key concepts: optimization, slope, descent.